© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21322
    Prev
    Next
    INDEX
    Explanations

    axis labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aths
    -0.06
    boro
    -0.05
    iet
    -0.05
     violations
    -0.05
     manc
    -0.05
     violation
    -0.05
    olina
    -0.05
     \(
    -0.05
    éĩįçļĦ
    -0.05
    çĻ½çļĦ
    -0.05
    POSITIVE LOGITS
    èĢĮå¤į
    0.07
    &R
    0.06
    site
    0.06
    umé
    0.06
    andle
    0.05
    thro
    0.05
    éĿ¢å¯¹çĿĢ
    0.05
    anita
    0.05
    çĮĸ
    0.05
     ÙĪÙĩÙħ
    0.05
    Activations Density 0.007%

    No Known Activations